Abhishek Mukhopadhyay, P. Biswas, Ayush Agarwal, Imon Mukherjee
Recent advancement in the field of computer vision and development of Deep Neural Network based object detection led researchers and industries to focus on autonomous vehicles. This paper aims to find how accurately previously proposed CNN architectures detect on-road obstacles in Indian road scenarios in the context of autonomous vehicle. We have compared three different convolution neural networks trained with COCO dataset for detecting autorickshaws in Indian road. We undertook statistical hypothesis testing to find effect of these three models, i.e. YOLOv3, Mask R-CNN, and RetinaNet on detection accuracy rate. While measuring accuracy, we have noted that detection accuracy rate of RetinaNet is significantly better than other two CNN architectures. Although there is no significant difference between other two networks in context of detection rate. The accuracy rate shows the performance of RetinaNet invariant to autorickshaws' color and shape, and different climatic and complex background scenarios.
{"title":"Performance Comparison of Different CNN models for Indian Road Dataset","authors":"Abhishek Mukhopadhyay, P. Biswas, Ayush Agarwal, Imon Mukherjee","doi":"10.1145/3338472.3338480","DOIUrl":"https://doi.org/10.1145/3338472.3338480","url":null,"abstract":"Recent advancement in the field of computer vision and development of Deep Neural Network based object detection led researchers and industries to focus on autonomous vehicles. This paper aims to find how accurately previously proposed CNN architectures detect on-road obstacles in Indian road scenarios in the context of autonomous vehicle. We have compared three different convolution neural networks trained with COCO dataset for detecting autorickshaws in Indian road. We undertook statistical hypothesis testing to find effect of these three models, i.e. YOLOv3, Mask R-CNN, and RetinaNet on detection accuracy rate. While measuring accuracy, we have noted that detection accuracy rate of RetinaNet is significantly better than other two CNN architectures. Although there is no significant difference between other two networks in context of detection rate. The accuracy rate shows the performance of RetinaNet invariant to autorickshaws' color and shape, and different climatic and complex background scenarios.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117195052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
NDN (Named Data Networking) is a new information-centric future network architecture. This new network architecture uses a "named content" mechanism instead of a "named host" mechanism based on TCP/IP networks. The mechanism decouples the geographic location from the identity identifier, while the transport content object itself is attached with security-related metadata. Compared with the traditional IP address-centric TCP/IP network, the information-centric NDN network is more suitable for high-speed dynamic VANET network environment. Therefore, we propose a secure content routing scheme for NOLSR in mobile networks. Despite the introduction of security mechanisms in NDN, these security mechanisms cannot meet the security requirements in wireless networks. In order to establish a secure routing mechanism in wireless dynamic networks, this paper uses identity-based cryptography for key distribution and management, and introduces some new security mechanisms, such as forward security mechanisms to reduce the threat of key leakage. Interest flooding will cause broadcast storm in wireless network. NOLSR adopts MPR mechanism for interest flooding. In order to reduce overhead in wireless mobile networks, LFBL (listen first-forward last) is adopted in MPR. To prevent the selection of the attacker-controlled node as the MPR node and the selection of the self-serving node in the MPR node, the malicious node and the self-private node are selected by using the trust value and voting mechanism between the computing nodes. Finally, this paper analyses the security attributes of NOLSR scheme, verifies the feasibility of NOLSR scheme in detail, and compares the efficiency of this scheme with other related schemes.
NDN (Named Data Networking)是一种以信息为中心的新型未来网络架构。这种新的网络架构使用“命名内容”机制，而不是基于TCP/IP网络的“命名主机”机制。该机制将地理位置与标识符解耦，而传输内容对象本身则附加了与安全相关的元数据。与传统的以IP地址为中心的TCP/IP网络相比，以信息为中心的NDN网络更适合高速动态的VANET网络环境。因此，我们提出了一种针对移动网络中NOLSR的安全内容路由方案。尽管在NDN中引入了安全机制，但这些安全机制不能满足无线网络的安全需求。为了在无线动态网络中建立安全的路由机制，本文采用基于身份的加密技术进行密钥分发和管理，并引入了一些新的安全机制，如前向安全机制，以减少密钥泄露的威胁。兴趣泛滥会引起无线网络的广播风暴。NOLSR采用MPR机制进行利益淹没。为了减少无线移动网络的开销，MPR中采用了LFBL(先听后听)。为了避免MPR节点选择攻击者控制的节点和MPR节点中自服务节点的选择，利用计算节点之间的信任值和投票机制选择恶意节点和自私有节点。最后，分析了NOLSR方案的安全属性，详细验证了该方案的可行性，并与其他相关方案进行了效率比较。
{"title":"Research on Secure Routing Technology Based on NDN for VANET","authors":"Xiaowei Gai","doi":"10.1145/3338472.3338495","DOIUrl":"https://doi.org/10.1145/3338472.3338495","url":null,"abstract":"NDN (Named Data Networking) is a new information-centric future network architecture. This new network architecture uses a \"named content\" mechanism instead of a \"named host\" mechanism based on TCP/IP networks. The mechanism decouples the geographic location from the identity identifier, while the transport content object itself is attached with security-related metadata. Compared with the traditional IP address-centric TCP/IP network, the information-centric NDN network is more suitable for high-speed dynamic VANET network environment. Therefore, we propose a secure content routing scheme for NOLSR in mobile networks. Despite the introduction of security mechanisms in NDN, these security mechanisms cannot meet the security requirements in wireless networks. In order to establish a secure routing mechanism in wireless dynamic networks, this paper uses identity-based cryptography for key distribution and management, and introduces some new security mechanisms, such as forward security mechanisms to reduce the threat of key leakage. Interest flooding will cause broadcast storm in wireless network. NOLSR adopts MPR mechanism for interest flooding. In order to reduce overhead in wireless mobile networks, LFBL (listen first-forward last) is adopted in MPR. To prevent the selection of the attacker-controlled node as the MPR node and the selection of the self-serving node in the MPR node, the malicious node and the self-private node are selected by using the trust value and voting mechanism between the computing nodes. Finally, this paper analyses the security attributes of NOLSR scheme, verifies the feasibility of NOLSR scheme in detail, and compares the efficiency of this scheme with other related schemes.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115530622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The article was written in the framework of the project entitled "Development of Police vehicles classification depending on their purpose and standardization of the central console of vehicles in the scope of arrangement and installation of ICT system and control devices of special purpose signals" DOB-BIO7/04/02/2015 with the value of PLN 4 058 789, co-funded by the National Centre for Research and Development under the contest 7/2015.
{"title":"Standardization of the Central Console in Police Vehicles","authors":"Piotr Łuka, A. Urban","doi":"10.1145/3338472.3338494","DOIUrl":"https://doi.org/10.1145/3338472.3338494","url":null,"abstract":"The article was written in the framework of the project entitled \"Development of Police vehicles classification depending on their purpose and standardization of the central console of vehicles in the scope of arrangement and installation of ICT system and control devices of special purpose signals\" DOB-BIO7/04/02/2015 with the value of PLN 4 058 789, co-funded by the National Centre for Research and Development under the contest 7/2015.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124311609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article has been removed from the ACM Digital Library because it was found to plagiarize an earlier work written by Eberhardt J., Tai S. (2017) On or Off the Blockchain? Insights on Off-Chaining Computation and Data. In: De Paoli F., Schulte S., Broch Johnsen E. (eds) Service-Oriented and Cloud Computing. ESOCC 2017. Lecture Notes in Computer Science, vol 10465. Springer, Cham https://link.springer.com/chapter/10.1007/978-3-319-67262-5_1 For further information, contact the ACM Director of Publications.
{"title":"Applying Modified SHA256 on Blockchain using Challenge Response and Off-chain Signatures Patterns","authors":"Maria Rona L. Perez, B. Gerardo, R. Medina","doi":"10.1145/3338472.3338486","DOIUrl":"https://doi.org/10.1145/3338472.3338486","url":null,"abstract":"This article has been removed from the ACM Digital Library because it was found to plagiarize an earlier work written by Eberhardt J., Tai S. (2017) On or Off the Blockchain? Insights on Off-Chaining Computation and Data. In: De Paoli F., Schulte S., Broch Johnsen E. (eds) Service-Oriented and Cloud Computing. ESOCC 2017. Lecture Notes in Computer Science, vol 10465. Springer, Cham https://link.springer.com/chapter/10.1007/978-3-319-67262-5_1 For further information, contact the ACM Director of Publications.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114875904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a light field image (LFI) encryption scheme based on pixel substitution and double random phase encoding (DRPE) is presented. The LFI includes the direction and intensity information of the light in the propagation process. Firstly, we employ an angular domain plane to represent the multi-view image of the LFI. Furthermore, pixel substitution processing based on rows and columns for a single view LFI. Finally, by the Fourier transform based on DRPE to obtain a encrypted image. Experimental results show that proposed scheme can be reliable and has a better immunity to noise and higher execution efficiency.
{"title":"Light Field Image Encryption Based on Pixel Substitution and Double Random Phase Encoding","authors":"Kangkang Wei, Wenying Wen","doi":"10.1145/3338472.3338477","DOIUrl":"https://doi.org/10.1145/3338472.3338477","url":null,"abstract":"In this paper, a light field image (LFI) encryption scheme based on pixel substitution and double random phase encoding (DRPE) is presented. The LFI includes the direction and intensity information of the light in the propagation process. Firstly, we employ an angular domain plane to represent the multi-view image of the LFI. Furthermore, pixel substitution processing based on rows and columns for a single view LFI. Finally, by the Fourier transform based on DRPE to obtain a encrypted image. Experimental results show that proposed scheme can be reliable and has a better immunity to noise and higher execution efficiency.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129197206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a hybrid model aiming to map input noise vector to the label of the generated image by Generative Adversarial Network (GAN). This model mainly consists of a pre-trained Deep Convolution Generative Adversarial Network (DCGAN) and a classifier. By using the model, we visualize the distribution of two-dimensional input noise leading to specific type of generated image after each training epoch of GAN. The visualization reveals the distribution feature of the input noise vectors and the performance of the generator. With this feature, we try to build a Guided Generator which can produce a fake image which we exactly need. Two methods are proposed to build the Guided Generator. One is the most significant noise (MSN) method, and another is utilizing labeled noise. MSN method can generate images precisely but with less variations. In contrast, labeled noise method can have more variations but slightly less stable.
{"title":"Design and Visualization of Guided GAN on MNIST dataset","authors":"Haohe Liu, Siqi Yao, Yulin Wang","doi":"10.1145/3338472.3338489","DOIUrl":"https://doi.org/10.1145/3338472.3338489","url":null,"abstract":"In this paper, we propose a hybrid model aiming to map input noise vector to the label of the generated image by Generative Adversarial Network (GAN). This model mainly consists of a pre-trained Deep Convolution Generative Adversarial Network (DCGAN) and a classifier. By using the model, we visualize the distribution of two-dimensional input noise leading to specific type of generated image after each training epoch of GAN. The visualization reveals the distribution feature of the input noise vectors and the performance of the generator. With this feature, we try to build a Guided Generator which can produce a fake image which we exactly need. Two methods are proposed to build the Guided Generator. One is the most significant noise (MSN) method, and another is utilizing labeled noise. MSN method can generate images precisely but with less variations. In contrast, labeled noise method can have more variations but slightly less stable.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134636584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a method for hiding information in audio signals by using singular spectrum analysis (SSA) with a psychoacoustic model to enhance the sound quality of a watermarked signal from our previous work. In this framework, an original signal is decomposed into many sub-signals by applying the combination of the SSA-based method and the psychoacoustic model. The sub-signals to be embedded are chosen using signal analysis based on human perception. The watermark bits are embedded into selected sub-signals by modifying some parts of their singular spectra according to an embedding rule. Then, the accuracy of extracted watermark bits and the sound quality of the watermarked signal, compared with that of the original one, are used to verify the performance of our framework. The experimental results show that the proposed framework satisfies the evaluation criteria in terms of inaudibility and robustness. However, it has a significant trade-off between them.
{"title":"Framework for Hiding Information in Audio Sub-signals by Using Singular Spectrum Analysis with Psychoacoustic Model","authors":"Ratthamontree Burimas, Tidanat Kumpuak, Mongkonchai Intarauksorn, Kasorn Galajit, P. Aimmanee, Jessada Karnjana","doi":"10.1145/3338472.3338488","DOIUrl":"https://doi.org/10.1145/3338472.3338488","url":null,"abstract":"This paper proposes a method for hiding information in audio signals by using singular spectrum analysis (SSA) with a psychoacoustic model to enhance the sound quality of a watermarked signal from our previous work. In this framework, an original signal is decomposed into many sub-signals by applying the combination of the SSA-based method and the psychoacoustic model. The sub-signals to be embedded are chosen using signal analysis based on human perception. The watermark bits are embedded into selected sub-signals by modifying some parts of their singular spectra according to an embedding rule. Then, the accuracy of extracted watermark bits and the sound quality of the watermarked signal, compared with that of the original one, are used to verify the performance of our framework. The experimental results show that the proposed framework satisfies the evaluation criteria in terms of inaudibility and robustness. However, it has a significant trade-off between them.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"PP 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126406963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of information technology and networks, images can be seen everywhere in life. When people browse magazines and the Internet, they come into contact with thousands of images, some of which remain in people's memories, while others are forgotten. Isola et al. first proposed the concept of image memorability and proved that image memorability is an intrinsic and stable attribute of images and can be shared among different viewers. Image memorability prediction has important research value and can be applied to education, advertising and other fields. In order to promote the research of image memorability prediction, the main theories and methods are summarized. Based on the comparison and analysis of the literatures related to image memorability prediction, this paper firstly reviews the proposal and quantification of the concept of image memorability. The features that affect the image memorability and the methods for extracting features are analyzed. The prediction of predictive image memorability is introduced in detail. The prediction is constructed based on Support Vector Machine and Convolution Neural Network and using different features that affect image memorability. Finally, the future work of image memorability is summarized and forecasted.
{"title":"Review of Image Memorability Prediction","authors":"Jie Liu, Dou-Dou Wang, Yan Wang, Hao Zhang","doi":"10.1145/3338472.3338479","DOIUrl":"https://doi.org/10.1145/3338472.3338479","url":null,"abstract":"With the development of information technology and networks, images can be seen everywhere in life. When people browse magazines and the Internet, they come into contact with thousands of images, some of which remain in people's memories, while others are forgotten. Isola et al. first proposed the concept of image memorability and proved that image memorability is an intrinsic and stable attribute of images and can be shared among different viewers. Image memorability prediction has important research value and can be applied to education, advertising and other fields. In order to promote the research of image memorability prediction, the main theories and methods are summarized. Based on the comparison and analysis of the literatures related to image memorability prediction, this paper firstly reviews the proposal and quantification of the concept of image memorability. The features that affect the image memorability and the methods for extracting features are analyzed. The prediction of predictive image memorability is introduced in detail. The prediction is constructed based on Support Vector Machine and Convolution Neural Network and using different features that affect image memorability. Finally, the future work of image memorability is summarized and forecasted.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lately, due to the increasing size of databases, several aspects have been studied in detail, such as grouping, searching for the closest neighbor and other identification methods. It has been found that in the multidimensional space, the concept of distance does not offer high performance. In this paper, we study the effect of different types of distances on the group to see the similarities between objects. Among these distances we mention two distances: the Euclidean distance and Manhattan distance, implemented in a system developed to identify the architectural styles of the buildings. The aim of this paper is using cluster analysis to identify distance metrics impact in detection of architectural styles using Data Mining techniques.
{"title":"A Survey of Distance Metrics in Clustering Data Mining Techniques","authors":"Marina Adriana Mercioni, S. Holban","doi":"10.1145/3338472.3338490","DOIUrl":"https://doi.org/10.1145/3338472.3338490","url":null,"abstract":"Lately, due to the increasing size of databases, several aspects have been studied in detail, such as grouping, searching for the closest neighbor and other identification methods. It has been found that in the multidimensional space, the concept of distance does not offer high performance. In this paper, we study the effect of different types of distances on the group to see the similarities between objects. Among these distances we mention two distances: the Euclidean distance and Manhattan distance, implemented in a system developed to identify the architectural styles of the buildings. The aim of this paper is using cluster analysis to identify distance metrics impact in detection of architectural styles using Data Mining techniques.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129927416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Saluja, Jeevithashree Dv, Somnath Arjun, P. Biswas, Teena Paul
This paper investigates eye gaze movements of children with different reading abilities due to learning disability. We analyzed eye gaze fixations using cluster analysis and velocity-based fixation classification algorithms. We used a non-invasive, screen mounted, low-cost eye tracker to collect data from 30 participants including students with learning disabilities. We analyzed raw gaze points, fixations and saccades, and noted that the density of gaze points around fixation. Total number of fixations and regressions (backward gaze movement) were statistically significantly correlated to the reading ability of students. We concluded that by analyzing different eye movements for a representative reading task, we can detect early signs of learning disabilities such as dyslexia.
{"title":"Analyzing Eye Gaze of Users with Learning Disability","authors":"K. Saluja, Jeevithashree Dv, Somnath Arjun, P. Biswas, Teena Paul","doi":"10.1145/3338472.3338481","DOIUrl":"https://doi.org/10.1145/3338472.3338481","url":null,"abstract":"This paper investigates eye gaze movements of children with different reading abilities due to learning disability. We analyzed eye gaze fixations using cluster analysis and velocity-based fixation classification algorithms. We used a non-invasive, screen mounted, low-cost eye tracker to collect data from 30 participants including students with learning disabilities. We analyzed raw gaze points, fixations and saccades, and noted that the density of gaze points around fixation. Total number of fixations and regressions (backward gaze movement) were statistically significantly correlated to the reading ability of students. We concluded that by analyzing different eye movements for a representative reading task, we can detect early signs of learning disabilities such as dyslexia.","PeriodicalId":142573,"journal":{"name":"Proceedings of the 3rd International Conference on Graphics and Signal Processing","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114627376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：